[ SKILLET · 18 skills ]
A skillet full of agent skills.
Production-tested workflows for auditing, improving, and shipping repos with AI coding agents. Repo audits with leverage-sorted backlogs, bug hunts that survive refutation, security sweeps, publish gates, releases, and memory handoffs. Plain SKILL.md files; every one extracted from a real workflow that broke the manual way.
Part of the Brigade fleet from Escoffier Labs
Three skills, one report contract. Run any of them alone or all three over time; the findings compose into a single leverage-sorted backlog. The trio is read-only by design, and expedite is the separate, opt-in step that drives the backlog to done.
/line-check
The flagship. A chef’s line check for your repo: seven stations scored (docs, agent-readiness, tests/CI, hygiene, structure, release hygiene, TODO mining) and a backlog sorted by impact relative to effort.
/bug-hunt
Correctness sweep across five lenses with mandatory adversarial verification. Only bugs that survive a refutation attempt make the report, each with a concrete trigger.
/security-sweep
Defensive security audit: secrets in tree and history, dependency CVEs, injection surfaces, authn/authz, exposure. Every finding ships with its remediation.
Report contract: docs/audit-report-format.md →
The daily build chain: design before code, plan before execution, execution with the checkboxes ticked live. Each handoff is written so a fresh session or a zero-context engineer can pick it up.
/taste
Test-first discipline that survives pressure. The failing test is watched failing before any implementation. Nothing leaves the kitchen untasted.
/refire
Root-cause-first debugging. Find out why the plate came back before cooking it again; three failed fixes means question the architecture.
/sendback
Review feedback with rigor instead of reflex: verify each claim against the codebase, push back with evidence, skip the performative agreement.
/stations
The expeditor’s fan-out for parallel agents: cluster by root cause, check write sets, give each station a complete ticket, taste the integrated result.
/pressure-test
Drives a plan to explicit decisions before anyone builds. Sous mode makes the reversible calls while you are AFK and leaves an auditable transcript.
/expedite
Takes an audit backlog and drives it to done: highest leverage first, one verified change at a time, anything destructive parked for you.
Nothing leaves the kitchen unchecked: gates for pull requests, public prose, repo publication, releases, and the knowledge a session leaves behind.
/pass
The gate before a pull request leaves your hands: real fix, tested, one concern, self-reviewed diff, and a PR body you approved.
/plate
The last look before prose goes public: scrubs hostnames, private IPs, leaked paths, and authorship tells from posts, PR bodies, and release notes.
/publish-readiness
The gate before a repo goes public: working-tree and git-history leak scans, hygiene checks, and the history-rewrite recipe when something already leaked.
/release-cut
Changelog roll-up, semver bump, tag, GitHub release, drafted announcement. Releases on request, never per feature.
/memory-handoff
Ends a session by writing durable knowledge into a structured handoff a memory owner can review and file. Pairs with Brigade, works standalone.
/skillify
The meta-skill: turn a script, runbook, or repeated workflow into a new skill, with a fresh-agent test before you call it done.
Skills are plain markdown. Install everything through the Claude Code marketplace, or copy individual SKILL.md folders into any compatible harness.
Claude Code
/plugin marketplace add escoffier-labs/skillet /plugin install skillet@skillet
Two commands in any session. Skills load on demand.
Any SKILL.md harness
git clone https://github.com/escoffier-labs/skillet cp -r skillet/skillet/skills/line-check <your-skills-dir>/
The skills are plain SKILL.md files. Copy what you want.
Per repo
cp -r skillet/skillet/skills/taste .claude/skills/
Drop individual skills into a repo to share them with everyone who works on it.
Then ask naturally ("audit this repo", "is this safe to publish", "cut a release") or invoke directly: /line-check, /security-sweep, /pressure-test.